No abstract

Object manipulation constitutes a large part of our daily hand movements. Recognition of such movements by a robot in an interactive scenario is an issue that is rapidly gaining attention. In this paper we present an approach to identification of a class of high-level manual object manipulations. Experiments have shown that the naive approach based on classification of low-level sensor data yields poor performance. In this paper we introduce a two-stage procedure that considerably improves the identification performance. In the first stage of the procedure we estimate an intermediate representation by applying a linear preprocessor to the multimodal low-level sensor data. This mapping calculates shape, orientation and weight estimators of the interaction object. In the second stage we generate a classifier that is trained to identify high-level object manipulations given the intermediate representation based on shape, orientation and weight. The devices used in our procedure are: Immersion CyberGlove II enhanced with five tactile sensors on the fingertips (TouchGlove), nine tactile sensors to measure the change of the object's weight and a VICON multicamera system for trajectory recording. We have achieved the following recognition rates for 3600 data samples representing a sequence of manual object manipulations: 100% correct labelling of "holding", 97% of "pouring", 81% of "squeezing" and 65% of "tilting".

We propose a hierarchical approach for Bayesian modeling and segmentation of continuous sequences of bimanual object manipulations. Based on bimodal (audio and tactile) low-level time series, the presented approach identifies semantically differing subsequences. It consists of two hierarchically executed stages, each of which employs a Bayesian method for unsupervised change point detection (Fearnhead, 2005). In the first step we propose to use a mixture of model pairs for bimanual tactile data. To this end, we select "object interaction" and "no object interaction" regions for the left and the right hand synchronously. In the second step we apply a set of Autoregressive (AR) models to the audio data. This allows us to select regions within "object interaction" segments according to qualitative changes in the audio signal. Two simple model types that allow the calculation of modality-specific segment likelihoods serve as a foundation for this modeling approach. Based on the acquired ground truth, empirical evaluation has showed that the generated segments correctly capture the semantic structure of the test time series. The developed procedure can serve as a building block for higher-level action and activity modeling frameworks.

No abstract

Abstract. In this paper we present a novel procedure for contour-based recognition of partially occluded three-dimensional objects. In our approach we use images of real and rendered objects whose contours have been deformed by a restricted change of the viewpoint. The preparatory part consists of contour extraction, preprocessing, local structure analysis and feature extraction. The main part deals with an extended construction and functionality of the classifier ensemble Adaptive Occlusion Classifier (AOC). It relies on a hierarchical fragmenting algorithm to perform a local structure analysis which is essential when dealing with occlusions. In the experimental part of this paper we present classification results for five classes of simple geometrical figures: prism, cylinder, half cylinder, a cube, and a bridge. We compare classification results for three classical feature extractors: Fourier descriptors, pseudo Zernike and Zernike moments.